DMX Desk / API
Get a token

Driving DMX Desk from code

Everything the web app does is available over HTTP. The base URL is https://api.skillsafe.ai/v1/app-api, every request carries Authorization: Bearer <token>, and every response is the same envelope.

The task field comes first

This app has five lanes behind one endpoint. Every run body must carry a task field naming the lane - it is what the system prompt routes on. Send the wrong one and you get a valid package of the wrong kind; omit it and the model picks the closest lane and tells you which it chose.

One more shape trap: the run body is the input object. Do not wrap it in an {"input": ...} envelope - that returns 200 while hiding task from the model, which is the most confusing way this API can fail.

taskLaneFieldsSections returned
planPatch against the packet, not the plotbrief, knownSummary, The Sheet, The Setting, Reasoning, Next Step
checkWhether this rig fits, and how fast it will runsheet, worrySummary, Verdict, Findings, Corrected Sheet, Next Step
packetWhere the refresh rate comes fromsheetSummary, What The Packet Costs, What The Refresh Allows, What Shortening It Buys, Next Step
patchWhere the fixtures land and what the edges wastesheetSummary, Group By Group, Where They Land, What The Boundaries Waste, Next Step
deliverDecide what changes: a mode, a universe, or nothingsheet, fixedSummary, A Mode Change Fixes, Only Another Universe Fixes, Nothing Fixes, Next Step

Only task and the lane's own required fields are mandatory: sheet on check, packet, patch and deliver; brief on plan. Every field is a string - there are no number fields on this app. The sheet is two blocks, a RIG block and a FIXTURES block, and the grammar is in /llms.txt and in the free panel on the app itself.

A FIXTURES row is id | what it is | count | slots each | why. The id, the description, the count and the slot width are all required; the why is not. The slot count is the width of the MODE, not a property of the fixture - the same LED par is 4 slots in one mode and 12 in another, and that is the number this whole app turns on. Take it from the fixture's mode table.

RIG takes name, universes, transport, send and fade. universes is a whole number of one or more. transport is dmx, artnet or sacn, and none of them changes the ceiling because an Ethernet node reclocks to DMX512 on its output. fade is the fade length to price for smoothness and a bare number is seconds; ms is accepted.

send is worth more than anything else on the sheet. full means every packet carries all 512 slots, which is what most consoles and nodes do; used means the packet stops at the highest patched slot. On a rig using half a universe that is the difference between 44.1 Hz and 87.63 Hz, and it is usually one setting.

Fixtures are patched first-fit in sheet order, because that is what a patch sheet follows. Each one takes CONTIGUOUS slots inside ONE universe, so a universe whose tail is narrower than the next fixture strands it - and the order you write the groups in changes how many fit. This is also why dividing the total by 512 gives the wrong universe count whenever a mode does not divide it.

A REFRESH RATE is quoted in Hz and a duration in ms or µs, and neither is ever written as the other. A fade's smoothness is reported in MOMENTS - the number of packet boundaries it spans - because that is what smoothness is, and it is not the number of values a bit depth offers.

Add $model to any body to choose the model for that run: gpt-5.6-luna, gpt-5.6-terra (the default) or gpt-5.6-sol. Luna caps output at 4,096 tokens and will fail the check and deliver lanes rather than shorten them - a findings table, a corrected sheet and three ranked tables is several thousand characters before the reasoning starts.

The response envelope

Success and failure have the same outer shape, so one check covers both.

{
  "ok": true,
  "data": {
    "...": "the result"
  }
}
{
  "ok": false,
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "seconds should be number, got string",
    "details": {}
  }
}
HTTPerror.codeWhat it means
400VALIDATION_ERRORThe body was not a JSON object, or a declared field had the wrong type. A number field sent as a string is the usual cause.
401UNAUTHORIZEDNo token, or a token that has expired or been revoked. Mint a new one.
402INSUFFICIENT_CREDITSThe balance is below the run's minimum. Call /estimate first and compare hold_credits against /me.
404NOT_FOUNDWrong path, or a job id that does not belong to this token.
409CONFLICTAn Idempotency-Key replay whose body differs from the original request.
429RATE_LIMITEDToo many requests. Back off; do not tight-loop.
503UPSTREAM_UNAVAILABLEThe model provider is unavailable. Retry with backoff.

1. Get a token

Open /tokens.html in a browser and copy the token this app already holds - no developer console needed. A guest token is minted automatically and is enough for /me and /estimate; writing a package is metered and needs a personal token, which comes from signing in on that page.

Keep it in an environment variable rather than in source:

export SKILLSAFE_TOKEN="YOUR_TOKEN"

2. Check the session and the balance

GET /me is free. It returns only three fields: subject_type, subject_id and credits. Signed-in means subject_type == "user" - there is no username or email to test.

curl -sS -X GET "https://api.skillsafe.ai/v1/app-api/me" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN"

3. Price the run before making it

POST /estimate costs nothing, creates no job, and returns the worst-case cost. Compare hold_credits against the balance from step 2 before you submit: a 402 after the fact is avoidable. hold_credits is a reservation priced at the full output cap - the actual charge is usually far lower.

It also echoes model, model_alias and markup_bps, which is the authoritative check that a run is bound to the model you think it is. Estimate each lane separately: their prompts and caps differ, so their holds do.

curl -sS -X POST "https://api.skillsafe.ai/v1/app-api/estimate" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "check",
  "sheet": "<a RIG block and a FIXTURES block - the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

4. Write a package

POST /run submits the job. Always send an Idempotency-Key: a network blip that replays the same request must not bill twice. A replay with the same key returns the stored result and is not charged again; a replay with the same key but a different body is a 409.

The response carries output.output (the Markdown package), charged_credits and truncated. If truncated is true the balance sat between min_credits and hold_credits and the output was cut short - render what arrived and say so rather than presenting it as complete.

curl -sS -X POST "https://api.skillsafe.ai/v1/app-api/run" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "check",
  "sheet": "<a RIG block and a FIXTURES block - the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

5. Stream a run

POST /run-stream is the same call with a text/event-stream response. Worth knowing before you build on it: from a server or from cURL you get event: delta frames carrying the output token by token; from a browser you get event: tick heartbeats and then one event: done with the whole output. Handle both, and treat ticks as liveness rather than progress.

Frame types are job (the job id), delta ({"text": "..."}), tick ({"t": seconds}), done, and error. An idempotent replay returns plain JSON with no stream at all, so check the content type before you start reading frames.

curl -sS -N -X POST "https://api.skillsafe.ai/v1/app-api/run-stream" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "Idempotency-Key: cbd-$(date +%s)" \
  -d '{
  "task": "check",
  "sheet": "<a RIG block and a FIXTURES block - the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

6. Read the result

output.output is Markdown in the envelope this app's system prompt guarantees: every section is a level-two heading spelled exactly as listed in the lane table above, in that order; tables are GitHub pipe tables with the declared columns; prompts are in fenced blocks opened with three backticks and the word text; checklists are - [x] lines.

So parsing is a split on /^## / - but do it fence-aware, because a prompt block can legitimately contain a line starting with ##. Count the sections you got against the ones the lane declares: a short list means the run was truncated, not that the contract changed.

def sections(md):
    out, name, buf, fence = {}, None, [], False
    for line in md.split("\n"):
        if line.lstrip().startswith("```"):
            fence = not fence
        if not fence and line.startswith("## "):
            if name:
                out[name] = "\n".join(buf).strip()
            name, buf = line[3:].strip(), []
            continue
        if name:
            buf.append(line)
    if name:
        out[name] = "\n".join(buf).strip()
    return out

The artifact most callers want is the fenced text block inside ## The Sheet or ## Corrected Sheet - that is a complete sheet in the grammar above, so it can be fed straight back into another lane with nothing carried alongside it. Every other section is prose and tables meant to be read.

Rate limits and good manners